© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 917
    Prev
    Next
    INDEX
    Explanations

    sequences of actions or events described in text

    oai_token-act-pair · gpt-3.5-turbo

    references to sequences and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburgh
    -0.86
    ryn
    -0.83
    sie
    -0.81
    aneers
    -0.79
    hoff
    -0.77
    nai
    -0.77
    aghd
    -0.73
    lisher
    -0.72
    fman
    -0.72
    isle
    -0.69
    POSITIVE LOGITS
     Sequence
    0.94
     sequence
    0.81
     repeats
    0.78
     unfold
    0.76
     sequences
    0.76
     electron
    0.72
     weaving
    0.70
    uality
    0.69
     divergence
    0.68
     consisting
    0.67
    Activations Density 0.048%

    No Known Activations